Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica
Reliable projections of sea-level rise depend on accurate representations of how fast-flowing glaciers slip along their beds. The mechanics of slip are often parameterized as a constitutive relation (or “sliding law”) whose proper form remains uncertain. Here, we present a novel deep learning-based...
Published in: | Journal of Advances in Modeling Earth Systems |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
American Geophysical Union
2021
|
Subjects: | |
Online Access: | https://authors.library.caltech.edu/111478/ https://authors.library.caltech.edu/111478/3/2021MS002621.pdf https://authors.library.caltech.edu/111478/4/2021ms002621-sup-0001-supporting%20information%20si-s01.pdf https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700 |
id |
ftcaltechauth:oai:authors.library.caltech.edu:111478 |
---|---|
record_format |
openpolar |
spelling |
ftcaltechauth:oai:authors.library.caltech.edu:111478 2023-05-15T13:36:58+02:00 Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica Riel, B. Minchew, B. Bischoff, T. 2021-11 application/pdf https://authors.library.caltech.edu/111478/ https://authors.library.caltech.edu/111478/3/2021MS002621.pdf https://authors.library.caltech.edu/111478/4/2021ms002621-sup-0001-supporting%20information%20si-s01.pdf https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700 en eng American Geophysical Union https://authors.library.caltech.edu/111478/3/2021MS002621.pdf https://authors.library.caltech.edu/111478/4/2021ms002621-sup-0001-supporting%20information%20si-s01.pdf Riel, B. and Minchew, B. and Bischoff, T. (2021) Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica. Journal of Advances in Modeling Earth Systems, 13 (11). Art. No. e2021MS002621. ISSN 1942-2466. doi:10.1029/2021MS002621. https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700 <https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700> cc_by CC-BY Article PeerReviewed 2021 ftcaltechauth https://doi.org/10.1029/2021MS002621 2021-11-18T19:04:55Z Reliable projections of sea-level rise depend on accurate representations of how fast-flowing glaciers slip along their beds. The mechanics of slip are often parameterized as a constitutive relation (or “sliding law”) whose proper form remains uncertain. Here, we present a novel deep learning-based framework for learning the time evolution of drag at glacier beds from time-dependent ice velocity and elevation observations. We use a feedforward neural network, informed by the governing equations of ice flow, to infer spatially and temporally varying basal drag and associated uncertainties from data. We test the framework on 1D and 2D ice flow simulation outputs and demonstrate the recovery of the underlying basal mechanics under various levels of observational and modeling uncertainties. We apply this framework to time-dependent velocity data for Rutford Ice Stream, Antarctica, and present evidence that ocean-tide-driven changes in subglacial water pressure drive changes in ice flow over the tidal cycle. Article in Journal/Newspaper Antarc* Antarctica Antarctica Journal Rutford Ice Stream Caltech Authors (California Institute of Technology) Rutford ENVELOPE(-85.300,-85.300,-78.600,-78.600) Rutford Ice Stream ENVELOPE(-80.000,-80.000,-79.167,-79.167) Journal of Advances in Modeling Earth Systems 13 11 |
institution |
Open Polar |
collection |
Caltech Authors (California Institute of Technology) |
op_collection_id |
ftcaltechauth |
language |
English |
description |
Reliable projections of sea-level rise depend on accurate representations of how fast-flowing glaciers slip along their beds. The mechanics of slip are often parameterized as a constitutive relation (or “sliding law”) whose proper form remains uncertain. Here, we present a novel deep learning-based framework for learning the time evolution of drag at glacier beds from time-dependent ice velocity and elevation observations. We use a feedforward neural network, informed by the governing equations of ice flow, to infer spatially and temporally varying basal drag and associated uncertainties from data. We test the framework on 1D and 2D ice flow simulation outputs and demonstrate the recovery of the underlying basal mechanics under various levels of observational and modeling uncertainties. We apply this framework to time-dependent velocity data for Rutford Ice Stream, Antarctica, and present evidence that ocean-tide-driven changes in subglacial water pressure drive changes in ice flow over the tidal cycle. |
format |
Article in Journal/Newspaper |
author |
Riel, B. Minchew, B. Bischoff, T. |
spellingShingle |
Riel, B. Minchew, B. Bischoff, T. Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica |
author_facet |
Riel, B. Minchew, B. Bischoff, T. |
author_sort |
Riel, B. |
title |
Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica |
title_short |
Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica |
title_full |
Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica |
title_fullStr |
Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica |
title_full_unstemmed |
Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica |
title_sort |
data-driven inference of the mechanics of slip along glacier beds using physics-informed neural networks: case study on rutford ice stream, antarctica |
publisher |
American Geophysical Union |
publishDate |
2021 |
url |
https://authors.library.caltech.edu/111478/ https://authors.library.caltech.edu/111478/3/2021MS002621.pdf https://authors.library.caltech.edu/111478/4/2021ms002621-sup-0001-supporting%20information%20si-s01.pdf https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700 |
long_lat |
ENVELOPE(-85.300,-85.300,-78.600,-78.600) ENVELOPE(-80.000,-80.000,-79.167,-79.167) |
geographic |
Rutford Rutford Ice Stream |
geographic_facet |
Rutford Rutford Ice Stream |
genre |
Antarc* Antarctica Antarctica Journal Rutford Ice Stream |
genre_facet |
Antarc* Antarctica Antarctica Journal Rutford Ice Stream |
op_relation |
https://authors.library.caltech.edu/111478/3/2021MS002621.pdf https://authors.library.caltech.edu/111478/4/2021ms002621-sup-0001-supporting%20information%20si-s01.pdf Riel, B. and Minchew, B. and Bischoff, T. (2021) Data-Driven Inference of the Mechanics of Slip Along Glacier Beds Using Physics-Informed Neural Networks: Case Study on Rutford Ice Stream, Antarctica. Journal of Advances in Modeling Earth Systems, 13 (11). Art. No. e2021MS002621. ISSN 1942-2466. doi:10.1029/2021MS002621. https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700 <https://resolver.caltech.edu/CaltechAUTHORS:20211015-222200700> |
op_rights |
cc_by |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.1029/2021MS002621 |
container_title |
Journal of Advances in Modeling Earth Systems |
container_volume |
13 |
container_issue |
11 |
_version_ |
1766086261967159296 |